Learning to flock through reinforcement

by   Mihir Durve, et al.

Flocks of birds, schools of fish, insects swarms are examples of coordinated motion of a group that arises spontaneously from the action of many individuals. Here, we study flocking behavior from the viewpoint of multi-agent reinforcement learning. In this setting, a learning agent tries to keep contact with the group using as sensory input the velocity of its neighbors. This goal is pursued by each learning individual by exerting a limited control on its own direction of motion. By means of standard reinforcement learning algorithms we show that: i) a learning agent exposed to a group of teachers, i.e. hard-wired flocking agents, learns to follow them, and ii) that in the absence of teachers, a group of independently learning agents evolves towards a state where each agent knows how to flock. In both scenarios, i) and ii), the emergent policy (or navigation strategy) corresponds to the polar velocity alignment mechanism of the well-known Vicsek model. These results show that a) such a velocity alignment may have naturally evolved as an adaptive behavior that aims at minimizing the rate of neighbor loss, and b) prove that this alignment does not only favor (local) polar order, but it corresponds to best policy/strategy to keep group cohesion when the sensory input is limited to the velocity of neighboring agents. In short, to stay together, steer together.


page 3

page 4


Multi-Robot Formation Control Using Reinforcement Learning

In this paper, we present a machine learning approach to move a group of...

Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents

Multi-agent reinforcement learning is difficult to be applied in practic...

PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control

This paper develops an efficient multi-agent deep reinforcement learning...

Modeling Social Group Communication with Multi-Agent Imitation Learning

In crowded social scenarios with a myriad of external stimuli, human bra...

Learning to Collaborate by Grouping: a Consensus-oriented Strategy for Multi-agent Reinforcement Learning

Multi-agent systems require effective coordination between groups and in...

Policy-Based Reinforcement Learning for Assortative Matching in Human Behavior Modeling

This paper explores human behavior in virtual networked communities, spe...

Broadcast Guidance of Agents in Deviated Linear Cyclic Pursuit

In this report we show the emergent behavior of a group of agents, order...

Please sign up or login with your details

Forgot password? Click here to reset